Unggi's picture
Upload README.md
eab90d2 verified
metadata
license: other
base_model: beomi/Llama-3-Open-Ko-8B
tags:
  - generated_from_trainer
model-index:
  - name: out-llama-8b-ko-slimorca_45000
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

base_model: beomi/Llama-3-Open-Ko-8B
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

# datasets:
#   - path: /workspace/axolotl/datasets/mix_corpus_extended_validated_stage1.json
#     type: completion
#     field: text
# /workspace/axolotl/datasets/slimorca_20000.jsonl
datasets:
  - path: /workspace/axolotl/datasets/slimorca_ko_45000.jsonl
    type: sharegpt
    conversation: chatml
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
eval_sample_packing: False
output_dir: ./out-llama-8b-ko-slimorca_45000

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 100
evals_per_epoch: 1
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|end_of_text|>

out-llama-8b-ko-slimorca_45000

This model is a fine-tuned version of beomi/Llama-3-Open-Ko-8B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8945

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 32
  • total_eval_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
1.0058 0.99 102 0.8945

Framework versions

  • Transformers 4.40.0.dev0
  • Pytorch 2.2.0+cu121
  • Datasets 2.15.0
  • Tokenizers 0.15.0